Senior Backend Engineer – Agents (USA Only - 100% Remote)

USA - Remote · Senior

Sponsorship not specifiedDetected 5 days ago

PythonGoRustPostgreSQLMongoDBTemporalLLMsRAGCRMCollaboration

About the role

We shipped our first agent, Chloe https://close.com/chloe, in 2026.
The team is running three major streams right now: Voice Agents, the LLM-powered chat assistant, and Custom Agents.
Most of the engineering problems here didn't exist a year ago.

You pick the right tool for the workload rather than retreating to what you know.
You have a POV on where they help and where they get in the way.
Not a researcher, but you can read one and tell us whether the result matters for our problem.

Python, Temporal, LangFuse, Pydantic, ElevenLabs, MCP, PostgreSQL, MongoDB - plus whichever LLM ships next.
No BS - Practice transparency and honesty, especially when it's hard
Discipline equals freedom - Keep your word to yourself and others
Strive for greatness - Constantly challenge yourself and others
Listen to our CEO and Founder, Steli Efti, tell the story of Close's journey in the $0-30m Blueprint https://www.close.com/blueprint.
In 2027, we're headed to Dusseldorf, Germany!
Explore our product.
Check out a demo https://www.close.com/demo-site!

Voice Agents, the LLM-powered chat assistant, and Custom Agents.
We're figuring them out in code, in production, in front of 11,000 paying customers.
Make deterministic and non-deterministic systems work together. Sales processes need steps that happen every single time; LLMs are bad at that. You'll help fuse our Workflows engine with agentic steps so customers get reliability where it matters and intelligence where it helps.
Handle the edges that make agents trustworthy. What happens to a fleet of running agents when a customer's AI credits run out? Pause semantics, recovery, and making sure nothing places a hundred calls that were supposed to happen last week.
Pick the right model for the job. We use many providers, test new models constantly, and are moving toward cost-aware routing - simple summarization jobs shouldn't run on frontier-priced models. You'll call when something is production-ready and when it's still a demo.

This listing is sourced directly from Close's careers page and normalized into a canonical job model.